Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8663
    Prev
    Next
    INDEX
    Explanations

    terms related to animal monitoring and trapping efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "catch" or "trap"

    np_acts-logits-general · gemini-2.0-flash

    catching or trapping animals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.64
     StatelessWidget
    -0.64
     שוליים
    -0.59
    τουργ
    -0.56
    migrationBuilder
    -0.54
    CopyWith
    -0.54
     aapt
    -0.53
     numberOfRows
    -0.52
     صوتيه
    -0.51
    AddColumn
    -0.51
    POSITIVE LOGITS
     catch
    2.03
     catching
    1.89
     catches
    1.77
    catch
    1.76
     capture
    1.76
     Catch
    1.76
     caught
    1.71
    Catch
    1.65
     trap
    1.63
    Catching
    1.62
    Activations Density 0.337%

    No Known Activations